Department of Otolaryngology-Head and Neck Surgery, University of Toronto, Toronto, Ontario, Canada.
Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.
JAMA Otolaryngol Head Neck Surg. 2022 Aug 1;148(8):764-772. doi: 10.1001/jamaoto.2022.1629.
Patient-reported symptom burden was recently found to be associated with emergency department use and unplanned hospitalization (ED/Hosp) in patients with head and neck cancer. It was hypothesized that symptom scores could be combined with administrative health data to accurately risk stratify patients.
To develop and validate a machine learning approach to predict future ED/Hosp in patients with head and neck cancer.
DESIGN, SETTING, AND PARTICIPANTS: This was a population-based predictive modeling study of patients in Ontario, Canada, diagnosed with head and neck cancer from January 2007 through March 2018. All outpatient clinical encounters were identified. Edmonton Symptom Assessment System (ESAS) scores and clinical and demographic factors were abstracted. Training and test cohorts were randomly generated in a 4:1 ratio. Various machine learning algorithms were explored, including (1) logistic regression using a least absolute shrinkage and selection operator, (2) random forest, (3) gradient boosting machine, (4) k-nearest neighbors, and (5) an artificial neural network. Data analysis was performed from September 2021 to January 2022.
The main outcome was any 14-day ED/Hosp event following symptom assessment. The performance of each model was assessed on the test cohort using the area under the receiver operator characteristic (AUROC) curve and calibration plots. Shapley values were used to identify the variables with greatest contribution to the model.
The training cohort consisted of 9409 patients (mean [SD] age, 63.3 [10.9] years) undergoing 59 089 symptom assessments (80%). The remaining 2352 patients (mean [SD] age, 63.3 [11] years) and 14 193 symptom assessments were set aside as the test cohort (20%). Several models had high predictive accuracy, particularly the gradient boosting machine (validation AUROC, 0.80 [95% CI, 0.78-0.81]). A Youden-based cutoff corresponded to a validation sensitivity of 0.77 and specificity of 0.66. Patient-reported symptom scores were consistently identified as being the most predictive features within models. A second model built only with symptom severity data had an AUROC of 0.72 (95% CI, 0.70-0.74).
In this study, machine learning approaches predicted with a high degree of accuracy ED/Hosp in patients with head and neck cancer. These tools could be used to accurately risk stratify patients and may help direct targeted intervention.
最近发现，患者报告的症状负担与头颈部癌症患者的急诊就诊和非计划性住院（ED/Hosp）有关。据推测，症状评分可以与管理式医疗健康数据相结合，以准确地对患者进行风险分层。
开发和验证一种机器学习方法，以预测头颈部癌症患者未来的 ED/Hosp。
设计、设置和参与者：这是一项基于人群的预测模型研究，对象为加拿大安大略省 2007 年 1 月至 2018 年 3 月期间诊断出头颈部癌症的患者。所有门诊临床就诊均被识别。提取了 Edmonton 症状评估系统（ESAS）评分以及临床和人口统计学因素。训练和测试队列以 4:1 的比例随机生成。探索了各种机器学习算法，包括（1）使用最小绝对收缩和选择算子的逻辑回归，（2）随机森林，（3）梯度提升机，（4）k-最近邻，以及（5）人工神经网络。数据分析于 2021 年 9 月至 2022 年 1 月进行。
主要结局是症状评估后 14 天内的任何 ED/Hosp 事件。使用接收者操作特征曲线（AUROC）下面积和校准图在测试队列上评估每个模型的性能。Shapley 值用于确定对模型贡献最大的变量。
训练队列包括 9409 名患者（平均[标准差]年龄为 63.3[10.9]岁），进行了 59089 次症状评估（80%）。其余 2352 名患者（平均[标准差]年龄为 63.3[11]岁）和 14193 次症状评估被留作测试队列（20%）。几种模型具有较高的预测准确性，特别是梯度提升机（验证 AUROC，0.80[95%CI，0.78-0.81]）。基于 Youden 的切点对应验证灵敏度为 0.77，特异性为 0.66。患者报告的症状评分始终被确定为模型中最具预测性的特征。仅使用症状严重程度数据构建的第二个模型的 AUROC 为 0.72（95%CI，0.70-0.74）。
在这项研究中，机器学习方法对头颈部癌症患者的 ED/Hosp 进行了高度准确的预测。这些工具可用于准确地对患者进行风险分层，并可能有助于指导有针对性的干预。
